Upload tokenizer
Browse files- special_tokens_map.json +3 -0
- tokenizer_config.json +6 -1
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,7 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": "<|endoftext|>",
|
| 3 |
"eos_token": "<|endoftext|>",
|
| 4 |
"unk_token": "<|endoftext|>"
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>"
|
| 4 |
+
],
|
| 5 |
"bos_token": "<|endoftext|>",
|
| 6 |
"eos_token": "<|endoftext|>",
|
| 7 |
"unk_token": "<|endoftext|>"
|
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"50256": {
|
|
@@ -10,11 +11,15 @@
|
|
| 10 |
"special": true
|
| 11 |
}
|
| 12 |
},
|
| 13 |
-
"additional_special_tokens": [
|
|
|
|
|
|
|
| 14 |
"bos_token": "<|endoftext|>",
|
| 15 |
"clean_up_tokenization_spaces": true,
|
| 16 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 17 |
"model_max_length": 1024,
|
|
|
|
| 18 |
"tokenizer_class": "GPT2Tokenizer",
|
| 19 |
"unk_token": "<|endoftext|>"
|
| 20 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"50256": {
|
|
|
|
| 11 |
"special": true
|
| 12 |
}
|
| 13 |
},
|
| 14 |
+
"additional_special_tokens": [
|
| 15 |
+
"<|endoftext|>"
|
| 16 |
+
],
|
| 17 |
"bos_token": "<|endoftext|>",
|
| 18 |
"clean_up_tokenization_spaces": true,
|
| 19 |
"eos_token": "<|endoftext|>",
|
| 20 |
+
"errors": "replace",
|
| 21 |
"model_max_length": 1024,
|
| 22 |
+
"pad_token": null,
|
| 23 |
"tokenizer_class": "GPT2Tokenizer",
|
| 24 |
"unk_token": "<|endoftext|>"
|
| 25 |
}
|